{"as_of":"2026-08-17T23:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd84a1038a5174b4f8a4e0b56e77bdef255dc691ce93ca15ca61bdbae0bf11c7","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:19:34.310295Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.11015/citation-record","integrity":"/paper/2608.11015/integrity","json":"/paper/2608.11015/citation-record.json","paper":"/paper/2608.11015"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.05862","last_updated":"2022-04-12T15:02:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-12T15:02:38Z","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.05862","snapshot_observed_at":"2026-08-15T14:19:33.938958Z","title":"Training a helpful and harmless assistant with reinforcement learning from human feedback.arXiv preprint arXiv:2204.05862, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.938958Z"},"links":{"cited_paper":"/paper/2204.05862","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:282bbce5d861cd4d81bc94224ee08a13603c576ed572781432c0dc46647f168a","observation_id":"389c538d-a068-461c-889e-30ea646df417","resolution":{"observed_at":"2026-08-15T14:19:33.938958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:33.949026Z","title":"From features to transformers: Redefining ranking for scalable impact.arXiv preprint arXiv:2502.03417, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.949026Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:625564680ab6fb4204f76dff3878d4cd8d385db217c665d4d0c23444497ae99d","observation_id":"44fed908-762d-4fc2-8b3f-82d7dce7d7b5","resolution":{"observed_at":"2026-08-15T14:19:33.949026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12102","last_updated":"2023-11-15T00:22:44Z","snapshot_observed_at":"2026-08-16T15:31:31.756430Z","submitted_at":"2023-05-20T05:35:40Z","title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12102","snapshot_observed_at":"2026-08-15T14:19:33.957454Z","title":"Chi, and Derek Zhiyuan Cheng","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.957454Z"},"links":{"cited_paper":"/paper/2305.12102","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:8928fe9de04a18e08bcd9ff0295dc3fe238358b1775d3c27c917888c47fa99b4","observation_id":"cadcce66-4ea4-40ff-98e4-a831070739b8","resolution":{"observed_at":"2026-08-15T14:19:33.957454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14135","last_updated":"2022-06-23T17:53:32Z","snapshot_observed_at":"2026-07-06T13:14:48.753329Z","submitted_at":"2022-05-27T17:53:09Z","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.14135","snapshot_observed_at":"2026-08-15T14:19:33.963400Z","title":"Fu, Stefano Ermon, Atri Rudra, and Christopher Ré","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.963400Z"},"links":{"cited_paper":"/paper/2205.14135","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:082d8edbf34cd914a8e0acdd44e1f4bfe64a8eaf1859c5eca3de54e992c31432","observation_id":"9301285f-1251-4b69-b7fe-c7983341f6e6","resolution":{"observed_at":"2026-08-15T14:19:33.963400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-15T14:19:33.972609Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.972609Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:7eaba3e3dd37b622a1ef3b36d339c514bb97e0b364215898b6fd9829a6aabeb4","observation_id":"a158981a-5c13-4e7a-9e11-97b73a54c74d","resolution":{"observed_at":"2026-08-15T14:19:33.972609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-15T14:19:33.982265Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.arXiv preprint arXiv:2501.12948, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.982265Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:1ee1fad62c972810995f68985ffa1d8bf294adc5907141b8fb269e2347cdd586","observation_id":"0bbfdd4f-39e5-4853-8981-952cd64d0d14","resolution":{"observed_at":"2026-08-15T14:19:33.982265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.004130Z","title":"Oxygenrec: An instruction-following generative framework for e-commerce recommendation.arXiv preprint arXiv:2512.22386, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.004130Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:af2918a8b61463ce545abc7986ad2c4de91ef635d2cbd655dd042aae8c08ec1d","observation_id":"142d5573-ad86-416e-9a9f-ec71af5156ab","resolution":{"observed_at":"2026-08-15T14:19:34.004130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.011186Z","title":"Chi, Cristos Goodrow, Ningren Han, He Ma, Romer Rosales, Abby Van Soest, Su-Lin Wu, Weilong Yang, and Yilin Zheng","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.011186Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:2f35013cd3188e3822c76797e4da9a0593356802eb18a5bc45baf9a21fbc6478","observation_id":"2d1748ba-3ac0-4bdb-a675-33a4302e6bc0","resolution":{"observed_at":"2026-08-15T14:19:34.011186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04245","last_updated":"2020-10-08T20:12:35Z","snapshot_observed_at":"2026-08-16T19:14:50.563961Z","submitted_at":"2020-10-08T20:12:35Z","title":"Query-Key Normalization for Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04245","snapshot_observed_at":"2026-08-15T14:19:34.019341Z","title":"Query-key normalization for transformers.Findings of EMNLP, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.019341Z"},"links":{"cited_paper":"/paper/2010.04245","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:6c1b8a2e3a51ae949a8faea208910207be19a918989147f922f9adabbd79b943","observation_id":"3b0d7346-f64f-4b96-b9a7-24754eb551e8","resolution":{"observed_at":"2026-08-15T14:19:34.019341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-15T14:19:34.026167Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.026167Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:8dafee57cf46fe892c108c18e590ea5c692cb70a891a089b063835db8df42f8c","observation_id":"cf2c04aa-d50c-48ee-8f10-48770a0cb15b","resolution":{"observed_at":"2026-08-15T14:19:34.026167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.039148Z","title":"Scaling recommender transformers to one billion parameters","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.039148Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:1af2e343a73d6bab710459d095d9b1439557f6b206f0c7d2132884577ace0571","observation_id":"a3442d5d-ba4a-4f0d-bc00-c33f8ff19b41","resolution":{"observed_at":"2026-08-15T14:19:34.039148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.00422","last_updated":"2026-05-29T23:17:34Z","snapshot_observed_at":"2026-08-17T07:19:38.733584Z","submitted_at":"2026-05-29T23:17:34Z","title":"UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.00422","snapshot_observed_at":"2026-08-15T14:19:34.045888Z","title":"Unipinrec: Unifying generative retrieval and ranking at pinterest scale.arXiv preprint arXiv:2606.00422, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.045888Z"},"links":{"cited_paper":"/paper/2606.00422","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:c3099ccb0b9beff973474537f95809c90d3d30d464279c70e7ed80bf70661bb0","observation_id":"fe49a203-9b18-48d0-93c2-a3e6fbbe7787","resolution":{"observed_at":"2026-08-15T14:19:34.045888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.25787","last_updated":"2026-04-28T15:56:11Z","snapshot_observed_at":"2026-08-12T23:21:20.447400Z","submitted_at":"2026-04-28T15:56:11Z","title":"Harmonizing Generative Retrieval and Ranking in Chain-of-Recommendation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.25787","snapshot_observed_at":"2026-08-15T14:19:34.053384Z","title":"Harmonizing generative retrieval and ranking in chain-of-recommendation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.053384Z"},"links":{"cited_paper":"/paper/2604.25787","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:4ae4d7a2db1387e6cb8595e75b5fbd7a6a381bdd0b8d836b9d40f36dfd83358e","observation_id":"f71a6ad6-f223-4186-98b1-12be40e27dd0","resolution":{"observed_at":"2026-08-15T14:19:34.053384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.11739","last_updated":"2024-11-18T17:08:35Z","snapshot_observed_at":"2026-08-12T18:09:47.205762Z","submitted_at":"2024-11-18T17:08:35Z","title":"QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.11739","snapshot_observed_at":"2026-08-15T14:19:34.061527Z","title":"Qarm: Quantitative alignment multi-modal recommendation at kuaishou.arXiv preprint arXiv:2411.11739, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.061527Z"},"links":{"cited_paper":"/paper/2411.11739","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:8439ee7643f4d51fda6bf20292f07b56ce72126d0f9ecf3347e2b7b894019b9e","observation_id":"64bd5b0f-966f-461c-b6c2-b92c9fc73d06","resolution":{"observed_at":"2026-08-15T14:19:34.061527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.07317","last_updated":"2026-06-08T08:58:58Z","snapshot_observed_at":"2026-08-13T07:14:53.785564Z","submitted_at":"2026-06-05T14:37:02Z","title":"Gated Bidirectional Linear Attention for Generative Retrieval","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.07317","snapshot_observed_at":"2026-08-15T14:19:34.069534Z","title":"Gated bidirectional linear attention for generative retrieval.arXiv preprint arXiv:2606.07317, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.069534Z"},"links":{"cited_paper":"/paper/2606.07317","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:ef5bf33b1e45966fe13e8a9477b09361fe191815a6334d879aafd6ef179a50aa","observation_id":"39261452-90be-481d-b74d-a137bb36b309","resolution":{"observed_at":"2026-08-15T14:19:34.069534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09332","last_updated":"2022-06-01T19:08:11Z","snapshot_observed_at":"2026-08-07T17:14:39.278754Z","submitted_at":"2021-12-17T05:43:43Z","title":"WebGPT: Browser-assisted question-answering with human feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09332","snapshot_observed_at":"2026-08-15T14:19:34.079095Z","title":"Webgpt: Browser-assisted question-answering with human feedback.arXiv preprint arXiv:2112.09332, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.079095Z"},"links":{"cited_paper":"/paper/2112.09332","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:d37c005f5916fe332132a5ac23276b097392e473000eb6fdcc060d87b3638646","observation_id":"70531d8e-e84d-4099-a713-bbf90ceba1d4","resolution":{"observed_at":"2026-08-15T14:19:34.079095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.086141Z","title":"Onerec technical report.arXiv preprint arXiv:2506.13695, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.086141Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:5966694fdb88a104df08759cfe0b4b7520b71a068ed5e5877a1fce3ceff8ad09","observation_id":"514b9b9c-b3c9-4f33-a33e-2876088946d3","resolution":{"observed_at":"2026-08-15T14:19:34.086141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02155","last_updated":"2022-03-04T07:04:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-03-04T07:04:42Z","title":"Training language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02155","snapshot_observed_at":"2026-08-15T14:19:34.091728Z","title":"Training language models to follow instructions with human feedback.Advances in Neural Information Processing Systems, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.091728Z"},"links":{"cited_paper":"/paper/2203.02155","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:0db31390c940d806432ab5c20c2684ad64347a3de29eb784b1368c1e6fc3ac8d","observation_id":"5c0a1900-e24f-4d90-a3fd-4881b07444a5","resolution":{"observed_at":"2026-08-15T14:19:34.091728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19755","last_updated":"2025-06-02T13:46:57Z","snapshot_observed_at":"2026-08-17T11:23:00.549399Z","submitted_at":"2025-05-26T09:33:54Z","title":"EGA-V1: Unifying Online Advertising with End-to-End Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19755","snapshot_observed_at":"2026-08-15T14:19:34.097992Z","title":"Ega-v1: Unifying online advertising with end-to-end learning.arXiv preprint arXiv:2505.19755, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.097992Z"},"links":{"cited_paper":"/paper/2505.19755","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:6b65c2776bf69659ccf92c6fcccc7328016b72862137db3d07339cd41edf8e72","observation_id":"9c7b6f80-3533-4ddc-bcf8-cf86a28d6fec","resolution":{"observed_at":"2026-08-15T14:19:34.097992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20215","last_updated":"2025-03-26T04:17:55Z","snapshot_observed_at":"2026-08-06T08:46:20.194739Z","submitted_at":"2025-03-26T04:17:55Z","title":"Qwen2.5-Omni Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20215","snapshot_observed_at":"2026-08-15T14:19:34.105805Z","title":"Qwen2.5-omni technical report.arXiv preprint arXiv:2503.20215, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.105805Z"},"links":{"cited_paper":"/paper/2503.20215","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:09f88196f6234144ca20f11e8822ffa5addbe3cdbbb5ab017d2e280492dff644","observation_id":"cbf096ba-e4a0-48cb-baf1-b8a38e553034","resolution":{"observed_at":"2026-08-15T14:19:34.105805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05065","last_updated":"2023-11-03T18:02:56Z","snapshot_observed_at":"2026-08-17T14:47:28.777073Z","submitted_at":"2023-05-08T21:48:17Z","title":"Recommender Systems with Generative Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05065","snapshot_observed_at":"2026-08-15T14:19:34.112260Z","title":"Recommender systems with generative 25 Sona Technical Report retrieval.Advances in Neural Information Processing Systems, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.112260Z"},"links":{"cited_paper":"/paper/2305.05065","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:e83302b511b94ff781e04760fcbd2714378da9d62e7df62c39452bc11e32c94c","observation_id":"bcdd2e94-0a46-40c5-9603-f8ae4854e696","resolution":{"observed_at":"2026-08-15T14:19:34.112260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-15T14:19:34.120655Z","title":"Glu variants improve transformer.arXiv preprint arXiv:2002.05202, 2020","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.120655Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:b5e6b3a268ea388b623c12d49fc839b6df4f52a0d7b8797c11fd7b7b4ad01a18","observation_id":"b2665a9a-8804-4bb0-b18f-fd2dc08e0666","resolution":{"observed_at":"2026-08-15T14:19:34.120655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09410","last_updated":"2021-09-24T23:19:02Z","snapshot_observed_at":"2026-08-16T18:38:23.650572Z","submitted_at":"2021-03-17T02:53:55Z","title":"Contrastive Learning of Musical Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.09410","snapshot_observed_at":"2026-08-15T14:19:34.126904Z","title":"Contrastive learning of musical representations.arXiv preprint arXiv:2103.09410, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.126904Z"},"links":{"cited_paper":"/paper/2103.09410","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:482bf006efc173f2f444a90c1d2aed44d9b77309f6339822f70ef5c5e6f82ce3","observation_id":"61a2aad3-5727-42ff-af10-de18443016d9","resolution":{"observed_at":"2026-08-15T14:19:34.126904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.01325","last_updated":"2022-02-15T19:09:36Z","snapshot_observed_at":"2026-08-17T15:45:31.564132Z","submitted_at":"2020-09-02T19:54:41Z","title":"Learning to summarize from human feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.01325","snapshot_observed_at":"2026-08-15T14:19:34.138059Z","title":"Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul Christiano","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.138059Z"},"links":{"cited_paper":"/paper/2009.01325","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:cf05c98dacb71cb4004c48c3f38bc6523459cbc4c4409e36f7d1bc7c01366903","observation_id":"e65250c0-53ba-43bb-bd0d-d6eeeaff86dc","resolution":{"observed_at":"2026-08-15T14:19:34.138059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09864","last_updated":"2023-11-08T13:36:32Z","snapshot_observed_at":"2026-08-17T06:56:20.644738Z","submitted_at":"2021-04-20T09:54:06Z","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09864","snapshot_observed_at":"2026-08-15T14:19:34.146704Z","title":"Roformer: Enhanced transformer with rotary position embedding.arXiv preprint arXiv:2104.09864, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.146704Z"},"links":{"cited_paper":"/paper/2104.09864","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:175e1fad598504b3aeb58f3655fbc1535d5210a36fdf57f73134afb10add5119","observation_id":"380d5509-d4e6-44f2-af95-23dfe2a6a9f7","resolution":{"observed_at":"2026-08-15T14:19:34.146704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.154454Z","title":"Grank: Towards target-aware and streamlined industrial retrieval with a generate-rank framework","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.154454Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:77d7425139faac5b42eb8bae6d8c71dd982cbccd537ef69292e463469def7b8b","observation_id":"bb0127c8-cb41-4e9f-aa88-548bef97d789","resolution":{"observed_at":"2026-08-15T14:19:34.154454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.08604","last_updated":"2026-06-09T13:50:48Z","snapshot_observed_at":"2026-07-06T23:48:07.065806Z","submitted_at":"2026-06-07T12:31:26Z","title":"Gryphon: A Unified Architecture for Semantic-ID Generation and Item-Level Scoring in Industrial Recommendations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.08604","snapshot_observed_at":"2026-08-15T14:19:34.161963Z","title":"Gryphon: A unified architecture for semantic-id generation and item-level scoring in industrial recommendations","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.161963Z"},"links":{"cited_paper":"/paper/2606.08604","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:ad17d0cbb081b1d25e296bf0de5f93e0fb694a5abd3962f46778ba6e236a2ef6","observation_id":"32fe102d-ee6a-40d2-b242-101946afb400","resolution":{"observed_at":"2026-08-15T14:19:34.161963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.168277Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.168277Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:7083deeb8b92943c73fbc88ccb1d6ea68c8b64040a800144f27ae065fc9f4097","observation_id":"ec510c90-c1b9-4d74-b5d8-f1578ca69282","resolution":{"observed_at":"2026-08-15T14:19:34.168277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.03699","last_updated":"2025-08-11T03:29:10Z","snapshot_observed_at":"2026-08-14T23:31:06.364354Z","submitted_at":"2025-06-04T08:31:33Z","title":"Scaling Transformers for Discriminative Recommendation via Generative Pretraining","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.03699","snapshot_observed_at":"2026-08-15T14:19:34.174783Z","title":"Scaling transformers for discriminative recommendation via generative pretraining.arXiv preprint arXiv:2506.03699, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.174783Z"},"links":{"cited_paper":"/paper/2506.03699","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:f24cc82ff08204130376305a56198fff68677dd81140b4dbdb481bfab43186e0","observation_id":"0b4cdb9b-bdaa-4185-b97a-16a180b6fe9a","resolution":{"observed_at":"2026-08-15T14:19:34.174783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.181762Z","title":"Onelive: Dynamically unified generative framework for live-streaming recommenda- tion.arXiv preprint arXiv:2602.08612, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.181762Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:c30c7845617016ff2602f7fa7c1f671499c3fbf81427068813e8faae36ca25eb","observation_id":"e9f1576c-9586-4a28-ae02-e96fc39e1582","resolution":{"observed_at":"2026-08-15T14:19:34.181762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.188972Z","title":"Learnable item tokenization for generative recommendation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.188972Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:a331b89454a38b9bd723b3039dbc16f55e9933ffd650742085ad6385d3f6751b","observation_id":"9ac4ac9f-f402-4146-9147-79c739f180bc","resolution":{"observed_at":"2026-08-15T14:19:34.188972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.14646","last_updated":"2025-08-20T11:57:48Z","snapshot_observed_at":"2026-08-15T17:07:08.493842Z","submitted_at":"2025-08-20T11:57:48Z","title":"OneLoc: Geo-Aware Generative Recommender Systems for Local Life Service","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.14646","snapshot_observed_at":"2026-08-15T14:19:34.197299Z","title":"Oneloc: Geo-aware generative recommender systems for local life service.arXiv preprint arXiv:2508.14646, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.197299Z"},"links":{"cited_paper":"/paper/2508.14646","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:5fd85ec0d5a53651d37a83ba05c0ab19e9dc1e1aabcdc269bc30aea480f5e1c0","observation_id":"b34d9942-eedd-487f-8a0b-16655b6398be","resolution":{"observed_at":"2026-08-15T14:19:34.197299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.217498Z","title":"On layer normalization in the transformer architecture","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.217498Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:96382dc5e6bc8f7506b1b5f0e0037e19e94786b4169bee9849b2060850d4169e","observation_id":"9a87d30b-2f05-47f1-a6b7-7b8ffdae2418","resolution":{"observed_at":"2026-08-15T14:19:34.217498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.224461Z","title":"On layer normalization in the transformer architecture","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.224461Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:a1c44c6771cc73ed6be358c14c6f23dd216d3c665a16ad88a286796a1d78c078","observation_id":"8d9fd769-d9de-4a82-8915-7b7abe1ae5a6","resolution":{"observed_at":"2026-08-15T14:19:34.224461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.230495Z","title":"Flashinfer: Efficient and customizable attention engine for LLM inference serving","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.230495Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:0d0a0e3ff8d7a8bcc97dd3d941b0836e6a75bbf2cb30bf421a992f6455180789","observation_id":"3a5e5283-c632-4216-8cf8-6fd6732e7eff","resolution":{"observed_at":"2026-08-15T14:19:34.230495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.235476Z","title":"Sampling-bias-corrected neural modeling for large corpus item recommendations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.235476Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:bc943a4f5af12eef637c7c3982b64da1901560358ef1e79a9193fa628f4cf7ea","observation_id":"14158f1e-e8d5-4777-9a71-5aefbf7863cf","resolution":{"observed_at":"2026-08-15T14:19:34.235476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17152","last_updated":"2024-05-06T02:05:45Z","snapshot_observed_at":"2026-08-16T20:04:50.187441Z","submitted_at":"2024-02-27T02:37:37Z","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17152","snapshot_observed_at":"2026-08-15T14:19:34.242011Z","title":"Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations.arXiv preprint arXiv:2402.17152, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.242011Z"},"links":{"cited_paper":"/paper/2402.17152","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:9c6c8c3dd6fd07f4c569c1f9f9e6bdd21900314ed4755847ea125a5f316a7482","observation_id":"df25f04c-822c-4b5b-b427-8c5c8697a4b9","resolution":{"observed_at":"2026-08-15T14:19:34.242011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07467","last_updated":"2019-10-16T16:44:22Z","snapshot_observed_at":"2026-08-08T08:22:25.110228Z","submitted_at":"2019-10-16T16:44:22Z","title":"Root Mean Square Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07467","snapshot_observed_at":"2026-08-15T14:19:34.250894Z","title":"Root mean square layer normalization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.250894Z"},"links":{"cited_paper":"/paper/1910.07467","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:02a42fc2ce75b2d8d657a14d86b67f839fb9959818be8eb6d770dc7fd5581c4c","observation_id":"4bfdcc5c-b6e2-4688-9bf4-803927c082a1","resolution":{"observed_at":"2026-08-15T14:19:34.250894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.257034Z","title":"Gpr: Towards a generative pre-trained one-model paradigm for large-scale advertising recommendation.arXiv preprint arXiv:2511.10138, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.257034Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:eeb667903390cf34a891ab0e853bdbcc5a1681d2caa7c4c705cfc7c1d33bac57","observation_id":"9faf4230-9d0a-4420-9017-b761b9127dd2","resolution":{"observed_at":"2026-08-15T14:19:34.257034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.262754Z","title":"Onemall: One architecture, more scenarios — end-to-end generative recommender family at kuaishou e-commerce.arXiv preprint arXiv:2601.21770, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.262754Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:b96ecadf486263671fb3e8ab4a59dd5a635fd4ec8f05d82e3471c12b66ad3aeb","observation_id":"da5e019b-b3fd-489e-a306-8f05797d6266","resolution":{"observed_at":"2026-08-15T14:19:34.262754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.276325Z","title":"Scaling user modeling: Large-scale online user representations for ads personalization in meta","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.276325Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:67eda22bdeaad5a4b20d1b1324703614b17d9ad62ce95326fd4f696ec2e6d1d5","observation_id":"2ce3e087-18c1-4081-8d18-195b8669b785","resolution":{"observed_at":"2026-08-15T14:19:34.276325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11277","last_updated":"2023-09-12T16:28:00Z","snapshot_observed_at":"2026-08-01T19:01:47.393546Z","submitted_at":"2023-04-21T23:52:27Z","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11277","snapshot_observed_at":"2026-08-15T14:19:34.295243Z","title":"Pytorch fsdp: Experiences on scaling fully sharded data parallel.arXiv preprint arXiv:2304.11277, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.295243Z"},"links":{"cited_paper":"/paper/2304.11277","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:1efa98e732de20f92f258b4d61209ad1a90173f24573c3c4a218ea0984b0bbe8","observation_id":"615d7edd-01b7-4310-8d94-d54cb695f288","resolution":{"observed_at":"2026-08-15T14:19:34.295243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.301800Z","title":"Enhancing embedding representation stability in recom- mendation systems with semantic id","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.301800Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:38b26777a8ffe709cb4c31e17a7a30442abf57d817aeab558c63f2f667c4a016","observation_id":"4abfa6b3-4cd0-4dc9-89ca-859e9bf04bbe","resolution":{"observed_at":"2026-08-15T14:19:34.301800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.17549","last_updated":"2025-06-01T14:54:02Z","snapshot_observed_at":"2026-08-17T02:27:12.398919Z","submitted_at":"2025-05-23T06:55:02Z","title":"EGA-V2: An End-to-end Generative Framework for Industrial Advertising","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.17549","snapshot_observed_at":"2026-08-15T14:19:34.310295Z","title":"Ega-v2: An end-to-end generative framework for industrial advertising.arXiv preprint arXiv:2505.17549, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.310295Z"},"links":{"cited_paper":"/paper/2505.17549","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:5334c23c6d0b154edeea8f181335c7f691f438bab50b14db47f9dc143be32cc6","observation_id":"1ae6b204-a9ee-46ab-a965-5a1b2f9084ff","resolution":{"observed_at":"2026-08-15T14:19:34.310295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09544","last_updated":"2024-05-22T08:41:51Z","snapshot_observed_at":"2026-08-16T14:42:50.484411Z","submitted_at":"2023-11-16T03:47:48Z","title":"Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09544","snapshot_observed_at":"2026-08-15T14:19:34.288069Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.288069Z"},"links":{"cited_paper":"/paper/2311.09544","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:5ee44b42a4d5333e78794ef9b2e16f164d2de3821df39d7503d306297ff607b3","observation_id":"0dfdc313-6031-4ef6-bfcf-fed6cc05eb38","resolution":{"observed_at":"2026-08-15T14:19:34.288069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18654","last_updated":"2025-08-22T05:21:30Z","snapshot_observed_at":"2026-08-16T07:53:31.454185Z","submitted_at":"2025-05-24T11:47:28Z","title":"MTGR: Industrial-Scale Generative Recommendation Framework in Meituan","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18654","snapshot_observed_at":"2026-08-15T14:19:33.998497Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:33.998497Z"},"links":{"cited_paper":"/paper/2505.18654","citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:2fe39682c6e4413efd538e4687cac45c579d83c9051a2bde2d530f2bee95db92","observation_id":"3ad2700a-7607-4f62-b321-ec7140653efc","resolution":{"observed_at":"2026-08-15T14:19:33.998497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:19:34.211736Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report","version":2},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-15T14:19:34.211736Z"},"links":{"citing_paper":"/paper/2608.11015"},"observation_digest":"sha256:c2a774299405ab27813d81fd26fe425a71d21dd2df9ae0ec1c10c87dcbc6878a","observation_id":"8668fc14-b0fc-43b8-aefc-6d5ed8eb6d08","resolution":{"observed_at":"2026-08-15T14:19:34.211736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.11015","last_updated":"2026-08-12T13:04:32Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-16T13:49:01.945432Z","submitted_at":"2026-08-11T14:58:26Z","title":"Sona Technical Report"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":47},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2608.11015."}